/// <summary>
/// Prevents Unnecessary File Indexing
/// </summary>
public static void PreventUnnecessaryFileIndex()
{
//ExStart: PreventUnnecessaryFileIndex
// Create index
Index index = new Index(Utilities.indexPath);
// Add documents to index
index.AddToIndex(Utilities.documentsPath);
// Try add the same documents to index
index.AddToIndex(Utilities.documentsPath); // Already indexed files will not be reindexed.
//ExEnd: PreventUnnecessaryFileIndex
}
/// <summary>
/// Shows how to filter files during indexing
/// Feature is supported in version 17.9.0 or greater of the API
/// </summary>
public static void FilterFilesDuringIndexing()
{
//ExStart:FilterFilesDuringIndexing
// Creating indexing settings object
IndexingSettings settings = new IndexingSettings();
// Creating filter that only passes files from 600 KB to 1 MB in length
DocumentFilter byLength = DocumentFilter.CreateFileLengthRange(614400, 1048576);
// Creating filter that only passes text files
DocumentFilter byExtension = DocumentFilter.CreateFileExtension(".txt");
// Creating composite filter that only passes text files from 600 KB to 1 MB in length
DocumentFilter compositeFilter = DocumentFilter.CreateConjunction(byLength, byExtension);
// Setting filter
settings.DocumentFilter = compositeFilter;
// Creating index
Index index = new Index(Utilities.indexPath, settings);
// Indexing
index.AddToIndex(Utilities.documentsPath);
//ExEnd:FilterFilesDuringIndexing
}
public void OpenFoundMessageUsingAsposeEmail(string searchString)
{
string myPstFile = Utilities.pathToPstFile;
// Indexing MS Outlook storage with email messages
Index index = new Index(Utilities.indexPath);
index.OperationFinished += Utilities.index_OperationFinished;
index.AddToIndex(myPstFile);
// Searching in index
SearchResults results = index.Search(searchString);
// User gets all messages that qualify to search query using Aspose.Email API
MessageInfoCollection messages = new MessageInfoCollection();
foreach (DocumentResultInfo searchResult in results)
{
if (searchResult.DocumentType == DocumentType.OutlookEmailMessage)
{
OutlookEmailMessageResultInfo emailResultInfo = searchResult as OutlookEmailMessageResultInfo;
MessageInfo message = GetEmailMessagesById(Utilities.pathToPstFile, emailResultInfo.EntryIdString);
if (message != null)
{
messages.Add(message);
}
}
}
}
/// <summary>
/// Creates index, adds documents to index and do regex search
/// </summary>
/// <param name="relevantKey">single keyword</param>
/// <param name="regexString">regex</param>
public static void RegexSearch(string relevantKey, string regexString)
{
//ExStart:Regexsearch
// Create index
Index index = new Index(Utilities.indexPath);
// Add documents to index
index.AddToIndex(Utilities.documentsPath);
// Search for documents where at least one word contain given regex
SearchResults searchResults1 = index.Search(relevantKey);
//Search for documents where present term1 or any email adress or term2
SearchResults searchResults2 = index.Search(regexString);
// List of found files
Console.WriteLine("Follwoing document(s) contain provided relevant tag: \n");
foreach (DocumentResultInfo documentResultInfo in searchResults1)
{
Console.WriteLine("Query \"{0}\" has {1} hit count in file: {2}", relevantKey, documentResultInfo.HitCount, documentResultInfo.FileName);
Console.WriteLine("Query \"{0}\" has {1} hit count in file: {2}", regexString, documentResultInfo.HitCount, documentResultInfo.FileName);
}
// List of found files
Console.WriteLine("Follwoing document(s) contain provided RegEx: \n");
foreach (DocumentResultInfo documentResultInfo in searchResults2)
{
Console.WriteLine("Query \"{0}\" has {1} hit count in file: {2}", relevantKey, documentResultInfo.HitCount, documentResultInfo.FileName);
Console.WriteLine("Query \"{0}\" has {1} hit count in file: {2}", regexString, documentResultInfo.HitCount, documentResultInfo.FileName);
}
//ExEnd:Regexsearch
}
/// <summary>
/// Shows how to implement own custom extractor for outlook document for the extension .ost and .pst files
/// </summary>
/// <param name="searchString">string to search</param>
public static void DetailedResults(string searchString)
{
//ExStart:DetailedResultsPropertyInDocuments
// Create or load index
Index index = new Index(Utilities.indexPath);
index.AddToIndex(Utilities.documentsPath);
SearchResults results = index.Search(searchString);
foreach (DocumentResultInfo resultInfo in results)
{
if (resultInfo.DocumentType == DocumentType.OutlookEmailMessage)
{
// for email message result info user should cast resultInfo as OutlookEmailMessageResultInfo for acessing EntryIdString property
OutlookEmailMessageResultInfo emailResultInfo = resultInfo as OutlookEmailMessageResultInfo;
Console.WriteLine("Query \"{0}\" has {1} hit count in message {2} in file {3}", searchString, emailResultInfo.HitCount, emailResultInfo.EntryIdString, emailResultInfo.FileName);
}
else
{
Console.WriteLine("Query \"{0}\" has {1} hit count in file {2}", searchString, resultInfo.HitCount, resultInfo.FileName);
}
foreach (DetailedResultInfo detailedResult in resultInfo.DetailedResults)
{
Console.WriteLine("{0}In field \"{1}\" there was found {2} hit count", "\t", detailedResult.FieldName, detailedResult.HitCount);
}
}
//ExEnd:DetailedResultsPropertyInDocuments
}
/// <summary>
/// Shows how to detect encoding selectively for some text files
/// Feature is supported in version 17.9.0 or greater
/// </summary>
public static void DetectEncodingSelectively()
{
//ExStart:DetectEncodingSelectively
// Creating index
Index index = new Index(Utilities.indexPath);
// Creating default encoding that is used when encoding was not detected
Encoding defaultEncoding = Encoding.GetEncoding(Encodings.Windows_1252);
// Subscribing to FileIndexing event
index.FileIndexing += (sender, args) =>
{
// Detecting encoding only for text files located in the 'documentsPath3' folder
string fileName = args.DocumentFullName;
if (fileName.EndsWith(".txt", true, CultureInfo.InvariantCulture) &&
fileName.StartsWith(Utilities.documentsPath3))
{
args.DetectEncoding(defaultEncoding, true);
}
};
// Indexing
index.AddToIndex(Utilities.documentsPath);
//ExEnd:DetectEncodingSelectively
}
/// <summary>
/// Creates index, adds documents to index and do search on the basis of synonyms by turning synonym search true
/// </summary>
/// <param name="searchString">string to search</param>
public static void SynonymSearch(string searchString)
{
//ExStart:SynonymSearch
// Create or load index
Index index = new Index(Utilities.indexPath);
// load synonyms
index.LoadSynonyms(Utilities.synonymFilePath);
index.AddToIndex(Utilities.documentsPath);
// Turning on synonym search feature
SearchParameters parameters = new SearchParameters();
parameters.UseSynonymSearch = true;
// searching for documents with words one of words "remote", "virtual" or "online"
SearchResults searchResults = index.Search(searchString, parameters);
// List of found files
foreach (DocumentResultInfo documentResultInfo in searchResults)
{
Console.WriteLine("Query \"{0}\" has {1} hit count in file: {2}", searchString, documentResultInfo.HitCount, documentResultInfo.FileName);
}
//ExEnd:SynonymSearch
}
/// <summary>
/// Shows how to perform accent insensitive indexing
/// Feature is supported in version 17.8.0 of the API
/// </summary>
public static void AccentInsensitiveIndexing()
{
//ExStart:AccentInsensitiveIndexing
// Enabling replacements during indexing
var settings = new IndexingSettings();
settings.UseCharacterReplacements = true;
// Creating index
Index index = new Index(Utilities.indexPath, settings);
// Clearing dictionary of replacements
index.Dictionaries.CharacterReplacements.Clear();
// Adding replacements
KeyValuePair <char, char>[] replacements = new KeyValuePair <char, char>[]
{
new KeyValuePair <char, char>('Ṝ', 'R'),
new KeyValuePair <char, char>('ṝ', 'r'),
};
index.Dictionaries.CharacterReplacements.AddRange(replacements);
// Import replacements from file. Existing replacements are staying.
index.Dictionaries.CharacterReplacements.Import(Utilities.replacementsFileName);
// Export replacements to file
index.Dictionaries.CharacterReplacements.Export(Utilities.exportedReplacementsFileName);
// Indexing
index.AddToIndex(Utilities.documentsPath);
//ExEnd:AccentInsensitiveIndexing
}
/// <summary>
/// Adds documents in books index
/// </summary>
public static void AddDocumentsInBooksIndex()
{
// Loading index
Index index = new Index(Utilities.booksIndex);
// Adding to index folder
index.AddToIndex(Utilities.documentsPath);
}
/// <summary>
/// Indexes separate files
/// </summary>
public static void IndexSeparateFiles()
{
//ExStart:IndexSeparateFiles
Index index = new Index(Utilities.indexPath);
// adding just one file to index
index.AddToIndex(Utilities.pathToPstFile);
//ExEnd:IndexSeparateFiles
}
/// <summary>
/// Merges Index with delta indexes Asynchronously to improve search performance
/// </summary>
public static void MergingIndexWithDeltaIndexesAsync()
{
//ExStart:MergingIndexWithDeltaIndexesAsync
string myDocumentsFolder1 = Utilities.documentsPath;
string myDocumentsFolder2 = Utilities.documentsPath2;
// Creating index
Index index = new Index(Utilities.indexPath, true);
// Adding documents to index
index.AddToIndex(myDocumentsFolder1);
// Adding one more folder to index. Delta index will be created.
index.AddToIndex(myDocumentsFolder2);
// Run merging asynchonously
index.MergeAsync();
//ExEnd:MergingIndexWithDeltaIndexesAsync
}
/// <summary>
/// Custom extractor test
/// </summary>
public static void CustomExtractor()
{
//ExStart:CustomExtractor
Index index = new Index(Utilities.indexPath);
index.CustomExtractors.Add(new CustomFieldExtractor());
index.AddToIndex(Utilities.documentsPath);
//ExEnd:CustomExtractor
}
public static void TotalHitCount(string searchString)
{
Index index = new Index(Utilities.indexPath);
index.AddToIndex(Utilities.documentsPath);
SearchResults results = index.Search(searchString);
Console.WriteLine("Searching with query \"{0}\" returns {1} documents with {2} total hit count", searchString, results.Count, results.TotalHitCount);
}
/// <summary>
/// Add document to index
/// </summary>
public static void AddDocumentToIndex()
{
//ExStart:AddDocumentToIndex
// Create index
Index index = new Index(Utilities.indexPath);
// all files from folder and its subfolders will be added to the index
index.AddToIndex(Utilities.documentsPath);
//ExEnd:AddDocumentToIndex
}
/// <summary>
/// Adds document to index with progress percentage event
/// </summary>
public static void GetIndexingProgressPercentage()
{
//ExStart:GetIndexingProgressPercentage
// Create index
Index index = new Index(Utilities.indexPath, true);
index.OperationProgressChanged += index_OperationProgressChanged; // event subscribing
// all files from folder and its subfolders will be added to the index
index.AddToIndex(Utilities.documentsPath);
//ExEnd:GetIndexingProgressPercentage
}
/// <summary>
/// Shows how to limit index report
/// Feature is supported in version 17.8.0 of the API
/// </summary>
public static void LimitIndexReport()
{
//ExStart:LimitIndexReport
Index index = new Index(Utilities.indexPath);
// Setting the maximum count of indexing reports
index.IndexingSettings.MaxIndexingReportCount = 2;
index.AddToIndex(Utilities.documentsPath);
index.AddToIndex(Utilities.documentsPath2);
index.AddToIndex(Utilities.documentsPath3);
// Getting indexing report. Array contains only 2 last records about indexing.
IndexingReport[] report = index.GetIndexingReport();
// Three indexing operations were performed, but only 2 last operations will be printed on the console in this example
foreach (IndexingReport record in report)
{
Console.WriteLine("Indexing takes {0}, index size: {1}.", record.IndexingTime, record.TotalIndexSize);
}
//ExEnd:LimitIndexReport
}
/// <summary>
/// Shows how to implement own custom extractor for outlook document for the extension .ost and .pst files
/// </summary>
/// <param name="searchString">string to search</param>
public static void OwnExtractorOst(string searchString)
{
//ExStart:OwnExtractorOst
// Create or load index
Index index = new Index(Utilities.indexPath);
index.CustomExtractors.Add(new CustomOstPstExtractor()); // Adding new custom extractor for container document
index.AddToIndex(Utilities.documentsPath); // Documents with "ost" and "pst" extension will be indexed using MyCustomContainerExtractor
SearchResults searchResults = index.Search(searchString);
//ExEnd:OwnExtractorOst
}
/// <summary>
/// Add PowerPoint Document to index
/// </summary>
public static void AddPowerPointDocumentToIndex()
{
//ExStart:AddPowerPointDocumentToIndex
// Create index
Index index = new Index(Utilities.indexPath);
// all files from folder and its subfolders will be added to the index
index.AddToIndex(Utilities.documentsPath);
SearchResults results1 = index.Search("author:cisco"); // searching by author of presentation
SearchResults results2 = index.Search("LastSavedBy:teresa"); // searching by person who saved presentation last time
//ExEnd:AddPowerPointDocumentToIndex
}
/// <summary>
/// Creates index,
/// Adds documents to index
/// Enable fuzzy search
/// Set similarity level from 0.0 to 1.0
/// Do Fuzzy search
/// </summary>
/// <param name="searchString">Misspelled string</param>
///
public static void FuzzySearch(string searchString)
{
//ExStart:Fuzzysearch
Index index = new Index(Utilities.indexPath);
index.AddToIndex(Utilities.documentsPath);
SearchParameters parameters = new SearchParameters();
// turning on Fuzzy search feature
parameters.FuzzySearch.Enabled = true;
// set low similarity level to search for less similar words and get more results
parameters.FuzzySearch.SimilarityLevel = 0.1;
SearchResults lessSimilarResults = index.Search(searchString, parameters);
Console.WriteLine("Results with less similarity level that is currently set to =" + parameters.FuzzySearch.SimilarityLevel);
foreach (DocumentResultInfo lessSimilarResultsDoc in lessSimilarResults)
{
Console.WriteLine(lessSimilarResultsDoc.FileName + "\n");
}
// set high similarity level to search for more similar words and get less results
parameters.FuzzySearch.SimilarityLevel = 0.9;
SearchResults moreSimilarResults = index.Search(searchString, parameters);
Console.WriteLine("Results with high similarity level that is currently set to =" + parameters.FuzzySearch.SimilarityLevel);
foreach (DocumentResultInfo highSimilarityLevelDoc in moreSimilarResults)
{
Console.WriteLine(highSimilarityLevelDoc.FileName + "\n");
}
/* // Create index
* Index index = new Index(Utilities.indexPath);
*
* // Add documents to index
* index.AddToIndex(Utilities.documentsPath);
*
* SearchParameters parameters = new SearchParameters();
* parameters.UseFuzzySearch = true; // obolete now it was in 1.1
*
* SearchResults searchResults = index.Search(searchString, parameters);
*
* foreach (DocumentResultInfo documentResultInfo in searchResults)
* {
* Console.WriteLine(documentResultInfo.FileName + "\n");
* }
*/
//ExEnd:Fuzzysearch
}
/// <summary>
/// adds documents to old version of the index
/// </summary>
public static void AddDocsToOldIndexVersion()
{
//ExStart:AddDocsToOldIndexVersion
// This index should be exist and should have one of previous version
string oldIndexFolder = Utilities.oldIndexFolderPath;
string documentsFolder = Utilities.documentsPath3;
// Load index
Index index = new Index(oldIndexFolder);
// Add documents to index. Index will be updated to actual version before adding new documents.
index.AddToIndex(documentsFolder, true);
//ExEnd:AddDocsToOldIndexVersion
}
internal static void IndexMetaData()
{
//ExStart: IndexMetaData
// Creating indexing settings object
IndexingSettings settings = new IndexingSettings();
settings.IndexType = IndexType.MetadataIndex;
// Creating index
Index index = new Index(Utilities.indexPath, settings);
// Indexing
index.AddToIndex(Utilities.documentsPath);
//ExEnd: IndexMetaData
}
/// <summary>
/// Break Index Repository using Cancellation Object
/// This method is supported by version 18.8 or greater
/// </summary>
public static void BreakIndexRepositoryUsingCancellationObject()
{
string documentsFolder = Utilities.documentsPath;
IndexRepository repository = new IndexRepository();
Index index = repository.Create();
index.AddToIndex(documentsFolder);
Cancellation cnc = new Cancellation();
// Updating all indexes in repository
repository.UpdateAsync(cnc);
// Canceling all operations in index repository
cnc.Cancel();
}
/// <summary>
/// Shows how to sutomatically detect encoding in text files
/// Feature is supported in version 17.9.0 or greater
/// </summary>
public static void AutomaticDetectEncoding()
{
//ExStart:AutomaticDetectEncoding
// Creating indexing settings object
IndexingSettings settings = new IndexingSettings();
// Enabling automatic encoding detection
settings.AutoDetectEncoding = true;
// Creating index
Index index = new Index(Utilities.indexPath, settings);
// Indexing
index.AddToIndex(Utilities.documentsPath);
//ExEnd:AutomaticDetectEncoding
}
/// <summary>
/// Creates a new books index, add documents in it and performs a search operation in it
/// </summary>
public static void SearchBooks()
{
// Creating index folder
Index index = new Index(Utilities.booksIndex);
// Indexing documents in folder
index.AddToIndex(Utilities.books);
// When indexing is finished user can search in it
SearchResults searchResults = index.Search("Gregor Samsa");
// List of found files
foreach (DocumentResultInfo result in searchResults)
{
Console.WriteLine((result.FileName));
}
}
/// <summary>
/// Tracks all the changes in the index folder
/// </summary>
public static void TrackAllChanges()
{
// Create index
Index index = new Index(Utilities.indexPath);
// Add documents to index
index.AddToIndex(Utilities.documentsPath);
// Remove some documents from documents path
// Edit some documents in documents path
// Add some new documents to documents path
index.Update();
// removed documents will be marked as deleted in index and will not be added to search results
// Edited documents will be reindexed
// Added documents will be added to index
}
/// <summary>
/// Merges several indexes asynchronously
/// </summary>
public static void MergingMultipleIndexesAsync()
{
//ExStart:MergingMultipleIndexesAsync
// Creating/loading first index
Index index1 = new Index(Utilities.mergeIndexPath1);
index1.AddToIndex(Utilities.documentsPath);
// Creating/loading second index
Index index2 = new Index(Utilities.mergeIndexPath2);
index2.AddToIndex(Utilities.documentsPath2);
// Merging data from index2 to index1. The index2 remains unchanged.
index1.MergeAsync(index2);
//ExEnd:MergingMultipleIndexesAsync
}
/// <summary>
/// The API implements safe updating of index files to increase reliability
/// Below example shows how to check if index should be reloaded
/// Feature is supported in version 17.10 or greater
/// </summary>
public static void CheckNeedForIndexReload()
{
//ExStart:CheckNeedForIndexReload
// Creating index
Index index = new Index(Utilities.indexPath);
// Indexing
index.AddToIndex(Utilities.documentsPath);
// Checking the need to reload
if (index.IndexStatus == IndexStatus.Failed)
{
// Reloading index
index = new Index(Utilities.indexPath);
}
//ExEnd:CheckNeedForIndexReload
}
/// <summary>
/// shows how to get indexing report
/// Feature is supported in version 17.7 or greater
/// </summary>
public static void GetIndexReport()
{
//ExStart:GetIndexReport
Index index = new Index(Utilities.indexPath);
index.AddToIndex(Utilities.documentsPath);
// Get indexing report
IndexingReport[] report = index.GetIndexingReport();
foreach (IndexingReport record in report)
{
Console.WriteLine("Indexing takes {0}, index size: {1}.", record.IndexingTime, record.TotalIndexSize);
}
//ExEnd:GetIndexReport
}
public static void MultiThreadedIndexing()
{
try
{
// Creating index
Index index = new Index(Utilities.indexPath);
// Indexing in 2 threads
index.AddToIndex(Utilities.documentsPath, 2);
// Searching
SearchResults result = index.Search("Einstein");
}
catch (Exception ex)
{
Console.WriteLine(ex.Message);
}
}
/// <summary>
/// Shows how to cache text of Indexed Documents in index
/// Feature is supported in version 17.9.0 or greater of the API
/// </summary>
public static void CacheTextOfIndexedDocsInIndex()
{
//ExStart:CacheTextOfIndexedDocsInIndex
// Creating indexing settings object
IndexingSettings settings = new IndexingSettings();
// Enabling source document text caching with normal compression level
// From version 17.10 onwards, value "High" has been added to GroupDocs.Search.Compression enumeration.
// So in order to cache document's text with high compression level use "Compression.High"
settings.TextStorageSettings = new TextStorageSettings(Compression.Normal);
// Creating index
Index index = new Index(Utilities.indexPath, settings);
// Indexing
index.AddToIndex(Utilities.documentsPath);
//ExEnd:CacheTextOfIndexedDocsInIndex
}
